OpenAI

Repositories

• gym

  A toolkit for developing and comparing reinforcement learning algorithms.
  Python 6,874 23,980 241 53 Updated Apr 18, 2021

• multiagent-particle-envs

  Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

  paper
  Python MIT 466 1,130 41 7 Updated Apr 17, 2021

• retro

  Retro Games in Gym
  C MIT 352 2,416 25 2 Updated Apr 17, 2021

• openai-python
  Python MIT 32 107 3 1 Updated Apr 16, 2021

• kubernetes

  Forked from kubernetes/kubernetes

  Production-Grade Container Scheduling and Management
  Go Apache-2.0 27,730 5 0 0 Updated Apr 16, 2021

• jukebox

  Code for the paper "Jukebox: A Generative Model for Music"

  audio music paper pytorch transformer generative-model vq-vae
  Python 628 4,283 130 7 Updated Apr 12, 2021

• CLIP

  Contrastive Language-Image Pretraining
  Jupyter Notebook MIT 315 3,320 18 0 Updated Apr 11, 2021

• DALL-E

  PyTorch package for the discrete VAE used for DALL·E.
  Python 278 2,467 4 2 Updated Apr 10, 2021

• mujoco-py

  MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
  Python 514 1,593 271 16 Updated Apr 8, 2021

• gpt-2

  Code for the paper "Language Models are Unsupervised Multitask Learners"

  paper
  Python 3,683 14,508 97 31 Updated Mar 31, 2021

• pixel

  Code for the single pixel debate game from the paper "AI safety via debate" (https://arxiv.org/abs/1805.00899)

  paper
  JavaScript MIT 16 35 0 6 Updated Mar 30, 2021

• InfoGAN

  Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

  paper
  Python 289 954 17 7 Updated Mar 25, 2021

• lm-human-preferences

  Code for the paper Fine-Tuning Language Models from Human Preferences
  Python MIT 33 162 3 3 Updated Mar 24, 2021

• CLIP-featurevis

  code for reproducing some of the diagrams in the paper "Multimodal Neurons in Artificial Neural Networks"
  Python 19 153 2 1 Updated Mar 21, 2021

• improved-diffusion

  Release for Improved Denoising Diffusion Probabilistic Models
  Python MIT 9 56 0 0 Updated Mar 17, 2021

• spinningup

  An educational resource to help anyone learn deep reinforcement learning.
  Python MIT 1,370 5,946 119 44 Updated Mar 16, 2021

• jeffwu-dotfiles

  Forked from WuTheFWasThat/dotfiles

  my configuration files
  Vim script 5 5 0 0 Updated Feb 25, 2021

• baselines

  OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
  Python MIT 3,967 11,397 386 68 Updated Feb 21, 2021

• gpt-2-output-dataset

  Dataset of GPT-2 outputs for research in detection, biases, and more
  Python MIT 306 1,122 10 2 Updated Feb 18, 2021

• glow

  Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

  paper
  Python MIT 475 2,759 51 10 Updated Feb 1, 2021

• summarize-from-feedback

  Code for "Learning to summarize from human feedback"
  Python 41 281 3 0 Updated Jan 27, 2021

• lustre

  Forked from Cray/lustre
  C 7 1 0 0 Updated Jan 27, 2021

• procgen

  Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
  C++ 85 474 2 1 Updated Jan 24, 2021

• robogym

  Robotics Gym Environments
  Python MIT 20 232 2 1 Updated Jan 6, 2021

• gym3

  Vectorized interface for reinforcement learning environments
  Python MIT 17 82 0 0 Updated Jan 2, 2021

• box2d-py

  Forked from jonasschneider/box2d-py
  C++ 15 20 0 2 Updated Dec 31, 2020

• blocksparse

  Efficient GPU kernels for block-sparse matrix multiplication and convolution
  Cuda MIT 149 805 32 3 Updated Dec 31, 2020

• coinrun

  Code for the paper "Quantifying Transfer in Reinforcement Learning"
  C++ 63 305 1 1 Updated Dec 30, 2020

• image-gpt
  Python 206 1,361 7 3 Updated Dec 28, 2020

• phasic-policy-gradient

  Code for the paper "Phasic Policy Gradient"
  Python MIT 18 126 0 0 Updated Dec 11, 2020